Research by Computer Scientists at Royal Holloway has been presented as part of the Emerging Artificial Intelligence (AI) Trends track at the AAAI 2026 EXPO in Singapore earlier this month.
AAAI (Association for the The Advancement of Artificial Intelligence conference series aims to promote research collaboration in AI
Our new lecturer in Computer Science, Dr Agnieszka Mensfelt, had her work accepted for presentation in the Emerging Trends in AI session at AAAI 2026 EXPO on 22 January, working together with a team from our department’s Neuro-symbolic AI group - Dr David Tena Cucala, Dr Santiago Franco, Dr Angeliki Koutsoukou-Argyraki, PhD student Vince Trencsenyi, and Prof Kostas Stathis.
Their recently published research paper “Towards a Common Framework for Autoformalization” reviews diverse instances of autoformalization with language models and proposes a unified framework that fosters collaboration across research areas to advance the development of next-generation AI neuro-symbolic systems.
The ultimate goal in proposing a unified framework is encouraging cross-pollination between different fields to advance the development of next generation AI systems. The work for the paper was supported by an international grant from the Leverhulme Trust.
The prestigious AAAI (Association for the Advancement of Artificial Intelligence) conference series aims to promote research collaboration in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines across the globe.
Autoformalization has emerged as a term referring to the automation of formalization—specifically, the formalization of mathematics using interactive theorem provers (proof assistants). Its rapid development has been driven by progress in deep learning, especially large language models (LLMs). More recently, the term has expanded beyond mathematics to describe the broader task of translating informal input into formal logical representations.
.
The extended version of the paper, which first appeared in NeLaMKRR’25, is available at this link here: https://arxiv.org/pdf/2509.09810
